Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    short meaningless names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Testing
    0.54
     testing
    0.52
     Hibernate
    0.45
    テスト
    0.43
     διάρκ
    0.42
     GABA
    0.41
     тест
    0.40
     Complexes
    0.40
     Еўропы
    0.40
    Testing
    0.40
    POSITIVE LOGITS
    a
    0.49
    Anonymous
    0.45
     menciona
    0.44
    localObject
    0.43
    jni
    0.42
    privacy
    0.42
    jacoco
    0.41
     eag
    0.41
    сто
    0.40
     teléfonos
    0.40
    Act Density 0.000%

    No Known Activations